Papers › Learning Black-Box Attackers with Transferable Priors and Query Feedback

Learning Black-Box Attackers with Transferable Priors and Query Feedback

21 Oct 2020NeurIPS 2020 12arXiv:2010.11742archive 2025-07-28

Jiancheng Yang, Yangzhou Jiang, Xiaoyang Huang, Bingbing Ni, Chenglong Zhao

This paper addresses the challenging black-box adversarial attack problem, where only classification confidence of a victim model is available. Inspired by consistency of visual saliency between different vision models, a surrogate model is expected to improve the attack performance via transferability. By combining transferability-based and query-based black-box attack, we propose a surprisingly simple baseline approach (named SimBA++) using the surrogate model, which significantly outperforms several state-of-the-art methods. Moreover, to efficiently utilize the query feedback, we update the surrogate model in a novel learning scheme, named High-Order Gradient Approximation (HOGA). By constructing a high-order gradient computation graph, we update the surrogate model to approximate the victim model in both forward and backward pass. The SimBA++ and HOGA result in Learnable Black-Box Attack (LeBA), which surpasses previous state of the art by considerable margins: the proposed LeBA significantly reduces queries, while keeping higher attack success rates close to 100% in extensive ImageNet experiments, including attacking vision benchmarks and defensive models. Code is open source at https://github.com/TrustworthyDL/LeBA.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2010.11742")

Code

Syntology Ran 3 of 19 code samples harvested from 1 repository linked to this paper; 16 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: official repository: 19 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

TrustworthyDL/LeBA officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested; 3 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
16unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from TrustworthyDL/LeBA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv1x1 TrustworthyDL/LeBA/imagenet/models/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report
conv3x3 TrustworthyDL/LeBA/imagenet/models/resnet.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · report
make_layers TrustworthyDL/LeBA/imagenet/models/vgg.py official repository ran · our draft was wrong Apache-2.0 (permissive) · eba3f5bcc6a06d36 · report
densenet121 TrustworthyDL/LeBA/imagenet/models/densenet.py official repository unverified Apache-2.0 (permissive) · f930d6c782c63d61 · report
densenet161 TrustworthyDL/LeBA/imagenet/models/densenet.py official repository unverified Apache-2.0 (permissive) · fadea15ec7227c0d · report
densenet169 TrustworthyDL/LeBA/imagenet/models/densenet.py official repository unverified Apache-2.0 (permissive) · 87e74274277809ca · report
distance TrustworthyDL/LeBA/LeBA10.py official repository unverified Apache-2.0 (permissive) · 312dffd937510c4d · report
gauss_conv TrustworthyDL/LeBA/LeBA10.py official repository unverified Apache-2.0 (permissive) · 82c759b04549c3fd · report
gauss_filter TrustworthyDL/LeBA/defense/defense.py official repository unverified Apache-2.0 (permissive) · 47c30b32ece499c8 · report
get_model TrustworthyDL/LeBA/imagenet/get_model.py official repository unverified Apache-2.0 (permissive) · cb1ea29b5c079739 · report
gkern TrustworthyDL/LeBA/LeBA10.py official repository unverified Apache-2.0 (permissive) · 5bccfafd65101cc6 · report
inception_v3 TrustworthyDL/LeBA/imagenet/models/inception.py official repository unverified Apache-2.0 (permissive) · 73c651617bcab7ae · report
jpeg_compression_batch TrustworthyDL/LeBA/defense/defense.py official repository unverified Apache-2.0 (permissive) · 5619a363090f64e7 · report
load_images_data TrustworthyDL/LeBA/data_utils.py official repository unverified Apache-2.0 (permissive) · b741e78d5646dc5b · report
normalize TrustworthyDL/LeBA/data_utils.py official repository unverified Apache-2.0 (permissive) · 88c8b61c9b4ccf9c · report
padding_layer_iyswim TrustworthyDL/LeBA/defense/defense.py official repository unverified Apache-2.0 (permissive) · edaf98a038f23e33 · report
resnet18 TrustworthyDL/LeBA/imagenet/models/resnet.py official repository unverified Apache-2.0 (permissive) · 8e33cb9411232a96 · report
vgg11 TrustworthyDL/LeBA/imagenet/models/vgg.py official repository unverified Apache-2.0 (permissive) · 4e473b974953d3d3 · report
vgg11_bn TrustworthyDL/LeBA/imagenet/models/vgg.py official repository unverified Apache-2.0 (permissive) · 4bafe38c1d715c07 · report

Tasks

Adversarial Attack

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections